The Patients' Voice in Clostridioides difficile Infection: Large Language Model-Assisted Thematic Analysis of Patient Testimonials.
- 1Division of Gastroenterology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA.
- 2Department of Medicine, Mount Auburn Hospital, Harvard Medical School, Cambridge, Massachusetts, USA.
- 3Division of Gastroenterology and Hepatology, Weill Cornell Medicine, New York, New York, USA.
Abstract
Background
Clostridioides difficile infection (CDI) imposes a burden that extends well beyond the gastrointestinal tract, yet existing outcome measures only partially capture the patient experience. We used frontier large language models (LLMs) on patient and caregiver narratives at scale to describe how burden shifts with disease course.Methods
We analyzed 189 testimonials from the Peggy Lillis Foundation corpus, sorted into 4 cohorts with recurrence (r) and fulminant (f) severity as axes (rfCDI, fCDI, rCDI, non-rfCDI). Two independent LLMs coded 8 thematic domains, 4 fulminant flags, 13 emerging semantic fields, the dominant dimension, and narrative arcs. Two physicians independently coded a subset for inter-rater reliability (PABAK, Gwet's AC1).Results
Treatment trajectory was the dominant theme in recurrent disease, whereas death and near-death dominated nonrecurrent fulminant narratives. Psychological burden was near-universal in fulminant disease (98.0% in rfCDI, 97.2% in fCDI). Caregiver and bereavement content concentrated in fCDI (66.7%). Diagnostic failure was frequent across recurrent cohorts (47.6-56.1%). Mentions of bacteriotherapy (fecal microbiota transplantation) concentrated in recurrent cohorts (60.2% rfCDI versus 5.6% fCDI). Financial, mental-health, and caregiver burdens were prominent and remain largely unaddressed by guidelines. Human-human reliability was substantial (PABAK 0.79 for semantic fields, 0.76 for domains); arc coding was least reliable.Conclusions
Patient narratives reveal a course-dependent, multidimensional burden in CDI. Concrete gaps exist between what patients prioritize, what guidelines recommend, and what therapy access provides. Frontier-LLM coding, validated against clinicians, offers a reproducible route to translate these priorities into research, care, and policy.
Related
- Epidemiology, risk factors and outcomes of Clostridioides difficile infection in a UK district general hospital: a retrospective cohort study
- Comparative Efficacy of Vancomycin and Fidaxomicin Regimens for the Prevention of Recurrent Clostridioides difficile Infection: A Systematic Review and Network Meta-Analysis of Randomized Controlled Trials
- Repurposing nystatin and taurocholate to target intracellular spore persistence during antibiotic treatment to prevent recurrent Clostridioides difficile infection.
- The Trajectory of Gastrointestinal Symptom Experience Following Fecal Microbiota Transplant for Recurrent Clostridioides Difficile Infection
- Faecalibacterium prausnitzii EXL01 Strain for the prevention of multiple-recurrent Clostridioides difficile Infection
BibTeX
@article{villafuertegalvez2026patients,
title = {{The Patients' Voice in Clostridioides difficile Infection: Large Language Model-Assisted Thematic Analysis of Patient Testimonials.}},
author = {Javier A Villafuerte-Gálvez and Marco A Noriega and Sena Cakir Colak and Carl V Crawford},
journal = {Open forum infectious diseases},
year = {2026},
month = oct,
doi = {10.1093/ofid/ofag650},
url = {https://europepmc.org/article/MED/42871751},
note = {CC BY},
}
RIS
TY - JOUR
TI - The Patients' Voice in Clostridioides difficile Infection: Large Language Model-Assisted Thematic Analysis of Patient Testimonials.
AU - Javier A Villafuerte-Gálvez
AU - Marco A Noriega
AU - Sena Cakir Colak
AU - Carl V Crawford
PY - 2026
DA - 2026/10/08
JO - Open forum infectious diseases
DO - 10.1093/ofid/ofag650
UR - https://europepmc.org/article/MED/42871751
AB - Background Clostridioides difficile infection (CDI) imposes a burden that extends well beyond the gastrointestinal tract, yet existing outcome measures only partially capture the patient experience. We used frontier large language models (LLMs) on patient and caregiver narratives at scale to describe how burden shifts with disease course.Methods We analyzed 189 testimonials from the Peggy Lillis Foundation corpus, sorted into 4 cohorts with recurrence (r) and fulminant (f) severity as axes (rfCDI, fCDI, rCDI, non-rfCDI). Two independent LLMs coded 8 thematic domains, 4 fulminant flags, 13 emerging semantic fields, the dominant dimension, and narrative arcs. Two physicians independently coded a subset for inter-rater reliability (PABAK, Gwet's AC1).Results Treatment trajectory was the dominant theme in recurrent disease, whereas death and near-death dominated nonrecurrent fulminant narratives. Psychological burden was near-universal in fulminant disease (98.0% in rfCDI, 97.2% in fCDI). Caregiver and bereavement content concentrated in fCDI (66.7%). Diagnostic failure was frequent across recurrent cohorts (47.6-56.1%). Mentions of bacteriotherapy (fecal microbiota transplantation) concentrated in recurrent cohorts (60.2% rfCDI versus 5.6% fCDI). Financial, mental-health, and caregiver burdens were prominent and remain largely unaddressed by guidelines. Human-human reliability was substantial (PABAK 0.79 for semantic fields, 0.76 for domains); arc coding was least reliable.Conclusions Patient narratives reveal a course-dependent, multidimensional burden in CDI. Concrete gaps exist between what patients prioritize, what guidelines recommend, and what therapy access provides. Frontier-LLM coding, validated against clinicians, offers a reproducible route to translate these priorities into research, care, and policy.
SN - 2328-8957
ER -